Shrooq Alsenan

Scopus Publications

Role of Optimization in RNA–Protein-Binding Prediction
Shrooq Alsenan, Isra Al-Turaiki, Mashael Aldayel, and Mohamed Tounsi
MDPI AG
RNA-binding proteins (RBPs) play an important role in regulating biological processes, such as gene regulation. Understanding their behaviors, for example, their binding site, can be helpful in understanding RBP-related diseases. Studies have focused on predicting RNA binding by means of machine learning algorithms including deep convolutional neural network models. One of the integral parts of modeling deep learning is achieving optimal hyperparameter tuning and minimizing a loss function using optimization algorithms. In this paper, we investigate the role of optimization in the RBP classification problem using the CLIP-Seq 21 dataset. Three optimization methods are employed on the RNA–protein binding CNN prediction model; namely, grid search, random search, and Bayesian optimizer. The empirical results show an AUC of 94.42%, 93.78%, 93.23% and 92.68% on the ELAVL1C, ELAVL1B, ELAVL1A, and HNRNPC datasets, respectively, and a mean AUC of 85.30 on 24 datasets. This paper’s findings provide evidence on the role of optimizers in improving the performance of RNA–protein binding prediction.

Automated System for Colon Cancer Detection and Segmentation Based on Deep Learning Techniques
Ahmad Taher Azar, Mohamed Tounsi, Suliman Mohamed Fati, Yasir Javed, Syed Umar Amin, Zafar Iqbal Khan, Shrooq Alsenan, and Jothi Ganesan
IGI Global
Colon cancer is one of the world's three most deadly and severe cancers. As with any cancer, the key priority is early detection. Deep learning (DL) applications have recently gained popularity in medical image analysis due to the success they have achieved in the early detection and screening of cancerous tissues or organs. This paper aims to explore the potential of deep learning techniques for colon cancer classification. This research will aid in the early prediction of colon cancer in order to provide effective treatment in the most timely manner. In this exploratory study, many deep learning optimizers were investigated, including stochastic gradient descent (SGD), Adamax, AdaDelta, root mean square prop (RMSprop), adaptive moment estimation (Adam), and the Nesterov and Adam optimizer (Nadam). According to the empirical results, the CNN-Adam technique produced the highest accuracy with an average score of 82% when compared to other models for four colon cancer datasets. Similarly, Dataset_1 produced better results, with CNN-Adam, CNN-RMSprop, and CNN-Adadelta achieving accuracy scores of 0.95, 0.76, and 0.96, respectively.

Deep Learning Reader for Visually Impaired
Jothi Ganesan, Ahmad Taher Azar, Shrooq Alsenan, Nashwa Ahmad Kamal, Basit Qureshi, and Aboul Ella Hassanien
MDPI AG
Recent advances in machine and deep learning algorithms and enhanced computational capabilities have revolutionized healthcare and medicine. Nowadays, research on assistive technology has benefited from such advances in creating visual substitution for visual impairment. Several obstacles exist for people with visual impairment in reading printed text which is normally substituted with a pattern-based display known as Braille. Over the past decade, more wearable and embedded assistive devices and solutions were created for people with visual impairment to facilitate the reading of texts. However, assistive tools for comprehending the embedded meaning in images or objects are still limited. In this paper, we present a Deep Learning approach for people with visual impairment that addresses the aforementioned issue with a voice-based form to represent and illustrate images embedded in printed texts. The proposed system is divided into three phases: collecting input images, extracting features for training the deep learning model, and evaluating performance. The proposed approach leverages deep learning algorithms; namely, Convolutional Neural Network (CNN), Long Short Term Memory (LSTM), for extracting salient features, captioning images, and converting written text to speech. The Convolution Neural Network (CNN) is implemented for detecting features from the printed image and its associated caption. The Long Short-Term Memory (LSTM) network is used as a captioning tool to describe the detected text from images. The identified captions and detected text is converted into voice message to the user via Text-To-Speech API. The proposed CNN-LSTM model is investigated using various network architectures, namely, GoogleNet, AlexNet, ResNet, SqueezeNet, and VGG16. The empirical results conclude that the CNN-LSTM based training model with ResNet architecture achieved the highest prediction accuracy of an image caption of 83%.

An Empirical Comparison of Machine and Deep Learning Algorithms' Performance on Chemical Data
Shrooq A. Alsenan
ACM
Chemoinfomratics is a field which is concerned with modelling chemical data using computational methods. Over the years, machine learning algorithms such as support vector machine and random forest have gained popularity in modelling chemical classification problems. However, the rapid development of deep learning algorithms and explosion of chemical and biological data, have contributed to an extensive growth of deep learning studies. This paper presents an empirical comparison between some machine learning and deep learning algorithms on chemical data. The comparison is conducted based on multiple accuracy measures to investigate their learning ability. Our empirical results provide evidence of deep learning models superiority over machine learning models.

IoT based Attendance Management System (AMS) with Smartwatches Compatibility
Shrooq Alsenan, Deem Saleh Aljameel, Sarah Arfaj Alsenan, and Dalal Fahad Al-Abdulaziz
ACM
The technological evolution and recent advances in machine learning have transformed how ordinary tasks are performed. Due to many technological, cultural and health related changes (such as Covid 19 pandemic), the means for managing attendance has been transformed with Internet of Things (IoT) based technologies. Attendance management system (AMS) is a system that documents and keeps track of employee and student hours and stores them on local repository or in the cloud. Manual approach to recording and keeping track of attendance is prone to human errors and time consuming. Although many studies have proposed new IoT biometric based solutions to enhance this process, achieving accuracy, efficiency and expense affordability can be a challenging task. The most used biometric approach recently is face recognition IoT solutions. Face recognition can be challenging during the Covid 19 pandemic because of face masks. Taking these issues into consideration, we propose a GPS-enabled Iris-based biometric approach for the attendance management system with smartwatches' compatibility feature. The system performs two main tasks: identification and real time localization. The identification is achieved with iris-based identification while localization is using GPS technology and smart watches. The proposed system addresses many fundamental issues such as the expense factors of manufacturing dedicated tracking wearable devices. It also provides an efficient means of identification using iris-based biometric identification which provides many advantages such as accuracy and enhanced friendly experience without relying on face recognition. The proposed IoT Attendance management systems will be designed to provide better automation for managing attendance and reduce many human errors resulting from manual approaches.

A Deep Learning Approach to Predict Blood-Brain Barrier Permeability
Shrooq Alsenan, Isra Al-Turaiki, and Alaaeldin Hafez
PeerJ
The blood–brain barrier plays a crucial role in regulating the passage of 98% of the compounds that enter the central nervous system (CNS). Compounds with high permeability must be identified to enable the synthesis of brain medications for the treatment of various brain diseases, such as Parkinson’s, Alzheimer’s, and brain tumors. Throughout the years, several models have been developed to solve this problem and have achieved acceptable accuracy scores in predicting compounds that penetrate the blood–brain barrier. However, predicting compounds with “low” permeability has been a challenging task. In this study, we present a deep learning (DL) classification model to predict blood–brain barrier permeability. The proposed model addresses the fundamental issues presented in former models: high dimensionality, class imbalances, and low specificity scores. We address these issues to enhance the high-dimensional, imbalanced dataset before developing the classification model: the imbalanced dataset is addressed using oversampling techniques and the high dimensionality using a non-linear dimensionality reduction technique known as kernel principal component analysis (KPCA). This technique transforms the high-dimensional dataset into a low-dimensional Euclidean space while retaining invaluable information. For the classification task, we developed an enhanced feed-forward deep learning model and a convolutional neural network model. In terms of specificity scores (i.e., predicting compounds with low permeability), the results obtained by the enhanced feed-forward deep learning model outperformed those obtained by other models in the literature that were developed using the same technique. In addition, the proposed convolutional neural network model surpassed models used in other studies in multiple accuracy measures, including overall accuracy and specificity. The proposed approach solves the problem inevitably faced with obtaining low specificity resulting in high false positive rate.

Auto-KPCA: A Two-Step Hybrid Feature Extraction Technique for Quantitative Structure-Activity Relationship Modeling
Shrooq A. Alsenan, Isra M. Al-Turaiki, and Alaaeldin M. Hafez
Institute of Electrical and Electronics Engineers (IEEE)
Quantitative structure–activity relationship (QSAR) modeling is an established approach for drug discovery, but many QSAR datasets suffer from the curse of dimensionality, a challenge that is usually addressed by using dimensionality reduction techniques such as principal component analysis (PCA). However, although linear feature extraction techniques have low computational cost and can handle linear relationships between descriptors, they cannot handle the complex structures found in QSAR data. Hybridization of feature extraction techniques is an effective approach to address the challenges of high-dimensional datasets, and combining the benefits of at least two dimensionality reduction techniques has been successful in many fields. This paper proposes Auto-KPCA, a two-step hybrid feature extraction technique that leverages (i) the fast computational capability of kernel PCA (KPCA) and (ii) the performance of a deep generalized autoencoder in handling complex data structures. Based on classification accuracy, the proposed approach is compared to other feature extraction techniques on the same benchmark dataset. The capability of Auto-KPCA is then investigated further by testing four deep-learning classification models, namely a convolutional neural network, a recurrent neural network, a feedforward deep neural network, and long short-term memory. To the best of the authors’ knowledge, this study is the first to investigate hybridization of KPCA and a deep generalized autoencoder in the context of QSAR. The reported results (i) provide invaluable insights regarding the behavior of different techniques in predicting class labels and (ii) demonstrate increased classification accuracy and noticeably decreased mean square error when compared with KPCA and autoencoders.

A Recurrent Neural Network model to predict blood–brain barrier permeability
Shrooq Alsenan, Isra Al-Turaiki, and Alaaeldin Hafez
Elsevier BV

Chemoinformatics for Data Scientists: An Overview
Shrooq A. Alsenan, Isra Al-Turaiki, and Alaaeldin Hafez
ACM
Shrooq A. Alsenan∗ 436203869@student.ksu.edu.sa Information Systems Department, College of Computer and Information Sciences, King Saud University Riyadh, Saudi Arabia Isra Al-Turaiki Information Technology Department, College of Computer and Information Sciences, King Saud University Riyadh, Saudi Arabia ialturaiki@ksu.edu.sa Alaaeldin Hafez Information Systems Department, College of Computer and Information Sciences, King Saud University Riydh, Saudi Arabia ahafez@ksu.edu.sa

Autoencoder-based Dimensionality Reduction for QSAR Modeling
Shrooq Alsenan, Isra Al-Turaiki, and Alaaeldin Hafez
IEEE
The recent advances in Machine Learning tools and algorithms have influenced fields including drug discovery. Nowadays, research conducted via trial- and-error experiments have been replaced by computational approaches. This growth prompted an undeniable development in synthesizing chemical data to support chemoinformatics research. One of the widely used tools to model chemoinformatics problems is Quantitative Structure-Activity Relationships (QSAR). Previous QSAR models were dealing with small datasets and limited number of features. Current QSAR datasets suffer from the problem of high dimensionality, where the number of features exceeds the number of records. Over the years, the curse of high dimensionality posed a major shortcoming in QSAR classification models. Linear Principle Component Analysis is a popular feature extraction method used to reduce the high dimensioanlity of QSAR datasets. However, QSAR datasets are highly complex and require deep understanding of features representation. Autoencoder is a type of neural networks that is not fully explored in QSAR modeling for dimensionality reduction purposes. In this research, we investigate the impact of autoencoder on a high dimensional QSAR dataset. The autoencoder performance is compared with PCA on the over all accuracy measure. Our preliminary analysis demonstrated that the proposed technique outperforms PCA.

Feature extraction methods in quantitative structure-activity relationship modeling: A comparative study
Shrooq A. Alsenan, Isra M. Al-Turaiki, and Alaaeldin M. Hafez
Institute of Electrical and Electronics Engineers (IEEE)
Computational approaches for synthesizing new chemical compounds have resulted in a major explosion of chemical data in the field of drug discovery. The quantitative structure–activity relationship (QSAR) is a widely used classification and regression method used to represent the relationship between a chemical structure and its activities. This research focuses on the effect of dimensionality-reduction techniques on a high-dimensional QSAR dataset. Because of the multi-dimensional nature of QSAR, dimensionality-reduction techniques have become an integral part of its modeling process. Principal component analysis (PCA) is a feature extraction technique with several applications in exploratory data analysis, visualization and dimensionality reduction. However, linear PCA is inadequate to handle the complex structure of QSAR data. In light of the wide array of current feature-extraction techniques, we perform a comparative empirical study to investigate five feature-extraction techniques: PCA, kernel PCA, deep generalized autoencoder (dGAE), Gaussian random projection (GRP), and sparse random projection (SRP). The experiments are performed on a high-dimensional QSAR dataset, which comprises 6394 features. The transformed low-dimensional dataset is inputted into a deep learning classification model to predict a QSAR biological activity. Three approaches are adopted to validate and measure the proposed techniques: (i) comparing the performance of the classification models, (ii) visualizing the relationship (correlation) between features in the low-dimension Euclidean space, and (iii) validating the proposed techniques using an external dataset. To the best of our knowledge, this study is the first to investigate and compare the aforementioned feature-extraction techniques in QSAR modeling context. The results obtained provide invaluable insights regarding the behavior of different techniques with both negative and positive classes. With linear PCA as a baseline, we prove that the investigated techniques substantially outperform the baseline in multiple accuracy measures and demonstrate useful ways of extracting significant features.

PERSO-retailer: Modeling the retailer's business data: Toward recommender system of retailers' marketing plan for personalized CMS
Shrooq Alsenan and Nesrine Zemirli
IEEE
This research aims to exploring the new research of personalized information access in the context of the online retailing. In this paper, we present PERSO-Retailer Modeler, the first stage in this line of research. We propose to add a new level of personalization in the Content Management System (CMS) application by not only creating an e-commerce website to run the retailer's business but by recommending the most relevant marketing plan to ensure the business success. In this perspective, the main advantage of our approach is to transform the traditional CMS into a personal assistant that fits the retailer's selling strategies for product offerings. Our methodology is based on hierarchical clustering of retailer's model, then using the frequent pattern mining techniques to identify common strategies used in a given cluster. The preliminary finding of our experimentation prototyping encourage us to proceed to the next stage of the research which is to propose an evaluation framework as well as exploring further data-mining techniques.

Statistical machine translation context modelling with recurrent neural network and LDA
Shrooq Alsenan and Mourad Ykhlef
Springer International Publishing

E-Commerce alarming security symptoms review and discussion of attacks indicators in e-commerce
Shrooq Alsenan and Abdulrahman Mirza
ACM
The research in the field of e-commerce security and cyber frauds is continually arising. Many measures were taken to facilitate dealing with security attacks to protect the e-commerce system as a whole. However, most of these measures work only after the attack took place. In this research, we take a new approach in identifying some symptoms relating to the e-commerce website, web-server or network that might be an alarming indicator that the e-commerce system is at risk. The correlation of the existence of these symptoms with security attacks is relatively high as we show in this study and is highly crucial for e-commerce websites operators to protect their e-commerce system as a whole. The preliminary contribution of this paper is being one of the first to investigate such alarming symptoms in the field of e-commerce to ultimately detect vulnerabilities causing security breaches to the e-commerce system before their occurrence.

PERSO-Retailer: Toward a Web Content Management System Based on a Personalized Marketing Recommender System for Retailers
Nesrine Zemirli and Shrooq Alsenan
IEEE
The growing incidence of web 2.0 challenges the traditional offline retailers to create a new method of shopping and new usage of consuming goods and services through a virtual shopping space over electronic store. A new contextual framework of customer and retailers relationship emerges through the aggregation and collaborative-shared opinion on the personal preferences about goods in the Web. While the benefits of building dynamic content into an e-commerce site are profound, the personalized access benefits are perhaps even bigger. Today more than ever, it is widely assumed that getting the relevant information at the right time, when it becomes available are the crucial issues and the main strategic challenges for improving the business prots. In this paper, we present an overview of PERSO- Retailer, a new research track, that aims to address the challenge of the growing competitive evolution of the marketplace and the access to the relevant resources at the right time, in the context of web 2.0. PERSO-Retailer is an innovative web-based framework for personalized online shopping experiences. Where the most of the recommendation system focus only in the final consumer side, our approach propose to tailor the recommendation by taking into account both the consumer as well as the retailer business profile. For that, our approach combines the contextualization and socialization of the user online experiences with the social merchandizing strategies of retailer. We propose novel frameworks that represent all the shopping dimensions of user, as well as the retailers business profile. In this perspective, the main advantage of our approach is to merge a new dimensions of retailer business selling strategies, the social merchandizing to the traditional online personalized recommendation system using multidimensional profile models for the consumer, the retailer and marketing plan for personalized selling strategies.

Hybrid CRM Deployment Model
Randah Altwegri, Fatmah Alsaleh, Shrooq Alsenan, and Samah Almutlaq
IEEE
Over the past few years, the options for buying, deploying and accessing business applications have increased dramatically, none more than the ones seeking effective Customer Relationship Management (CRM) solution. The new environment of running CRM in the cloud has been in use for several years and the tendency of using cloud CRM and cloud computing in general is continuously growing. However, concerns about the data security and privacy still an issue for some companies. In this paper, we briefly propose a hybrid model that combines On Premise and Cloud CRM while highlighting their major capabilities in keeping today's businesses performing efficiently and securely. Then, a closer look is taken to exploring the hybrid model through number of CRM's main functions illustrated on a dynamic arc.

Shrooq Alsenan

EDUCATION

RESEARCH, TEACHING, or OTHER INTERESTS

Scopus Publications